Belt running monitoring method and system for a tower-type pumping unit

Abstract

The present application relates to pumping unit belt monitoring technical field, specifically relates to a kind of tower type pumping unit belt operation monitoring method and system.The method obtains the weight distance, temperature data and local image of belt at each time, and the average load of each working cycle;Average weight distance is obtained based on weight distance;According to the average weight distance difference of each working cycle and the first working cycle, the temperature data and average load of each working cycle, the aging degree of belt is obtained, and then the belt damage parameter at the end of current working cycle is judged whether there is damage to belt, if there is damage, according to the gray value of pixel in local image in current working cycle, the belt damage condition at the end of current working cycle is obtained.The present application more accurately and comprehensively and timely analyzes the damage condition in belt through the weight distance and local image of belt in each working cycle, ensures the working efficiency of tower type pumping unit.

Description

Technical Field

[0001] This invention relates to the field of oil pumping unit belt monitoring technology, specifically to a method and system for monitoring the operation of a tower-type oil pumping unit belt. Background Technology

[0002] The belts of tower pumping units are a critical transmission component in oil extraction operations, and are typically made of steel cord with a rubber core. Due to prolonged load application and material aging, tower pumping unit belts may experience wear, deformation, and breakage, posing a threat to the safety of the equipment and operators. Therefore, regular inspection and maintenance of the tower pumping unit belts are necessary. However, downtime for inspection and maintenance requires significant manpower and time, impacting the pumping unit's efficiency; furthermore, belt damage is a slow process, making it difficult to detect problems promptly during inspection and maintenance.

[0003] Chinese Patent Publication No. CN117167448B discloses a tower-type pumping unit belt system with a safety anti-breakage and anti-detachment device, which overcomes the problem of poor accuracy in early warning of safety hazards such as belt breakage and detachment in existing technologies. The structure of the tower-type pumping unit belt system with the safety anti-breakage and anti-detachment device includes a lazy rope, a load-bearing rope, a wireless tension sensor, an NB-IoT wireless sensor, a lazy rope counterweight fixing block, a lazy rope roller fixing block, a belt, a belt roller fixing block, a belt counterweight fixing block, and a data processing module. The wireless tension sensor is used to detect the tension of the lazy rope, and the NB-IoT wireless sensor is used to detect the temperature and vibration frequency of the belt. The data processing module acquires and analyzes these data, and based on the analysis results, provides early warning of safety hazards during belt operation and determines the early warning method.

[0004] Existing technologies disclose real-time monitoring methods for the belt operation status of tower-type pumping units based on lazy ropes, wireless tension sensors, and NB-IoT wireless sensors. However, these technologies have the following problems: First, when the lazy rope is fixed close to the belt, friction between the rope and the belt can easily occur; when the rope is fixed too far from the belt, the rope tension may not accurately reflect the degree of belt deformation. Second, the wireless tension sensor and NB-IoT wireless sensor need to be fixed to the belt and counterweight, and the lazy rope roller needs to rotate synchronously with the belt roller, resulting in insufficient flexibility in installation and disassembly. Third, the lazy rope can only monitor the longitudinal deformation of the belt, and its ability to provide early warning of belt surface delamination and cracking is insufficient. Therefore, existing technologies cannot flexibly, accurately, and timely detect belt damage in tower-type pumping units, nor can they provide timely warnings of potential safety hazards during belt operation, thus failing to guarantee the safety of equipment operation and operators. Summary of the Invention

[0005] To address the technical problem that existing technologies struggle to flexibly, accurately, and promptly detect belt damage in tower-type pumping units, thus failing to provide timely early warnings of potential safety hazards during belt operation, this invention aims to provide a belt operation monitoring method and system for tower-type pumping units. The specific technical solution adopted is as follows: In a first aspect, one embodiment of the present invention provides a method for monitoring the belt operation of a tower-type pumping unit, the method comprising the following steps: The system acquires real-time data on the counterweight distance, temperature, and local images of the belt of the tower-type pumping unit at each moment during each work cycle, as well as the average load on the belt during each work cycle; where the counterweight distance is the distance between the counterweight and the upper platform. Based on the counterweight distance of the belt in each work cycle, obtain the average counterweight distance of each work cycle; based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data and average load of each work cycle, and the initial length of the belt, obtain the belt aging degree at the end of each work cycle. Based on the belt aging level at the end of the current work cycle and the belt aging level at the end of each previous historical work cycle, obtain the belt damage parameters at the end of the current work cycle. Based on the belt damage parameters, determine whether there is belt damage at the end of the current work cycle. If damage is determined, obtain the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in the local image during the current work cycle.

[0006] Furthermore, the method for obtaining the average counterweight distance is as follows: For any working cycle of the belt, the average counterweight distance of that working cycle is obtained based on the counterweight distance in that working cycle; The formula for calculating the average counterweight distance is as follows: In the formula, The average counterweight distance during the c-th work cycle; Let c be the duration of the c-th work cycle; The distance of the counterweight at time t in the c-th work cycle; To perform calculus on the counterweight distance in the c-th work cycle.

[0007] Furthermore, the method for obtaining the degree of belt aging is as follows: For any working cycle of the belt, obtain the difference between the average counterweight distance of this working cycle and the first working cycle, and use it as the first value; The ratio of the first value to the initial length is taken as the average strain increment at the end of the working cycle. The average of the temperature data at all times in the work cycle is used as the target temperature data for the work cycle. The standard belt average strain for this working cycle is obtained by using the target temperature data and average load for this working cycle. The ratio of the average strain increment to the average strain of the standard belt is used as the belt aging degree at the end of the working cycle.

[0008] Furthermore, the method for obtaining the belt damage parameters is as follows: The belt aging degree at the end of the current work cycle is arranged with the belt aging degree at the end of each previous historical work cycle according to the order of the work cycles to obtain the belt aging degree sequence. The elements in the belt aging degree sequence are fitted into a curve, and the tangent slope of each belt aging degree on the curve is obtained. The tangent slope is divided by the maximum inter-class variance to obtain the first category and the second category. The difference between the mean of all tangent slopes in the first category and the mean of all tangent slopes in the second category is taken as the degree of belt aging mutation at the end of the current work cycle. The difference between the standard deviation of all tangent slopes in the first category and the standard deviation of all tangent slopes in the second category is taken as the degree of belt aging increase at the end of the current work cycle; The sum of the abrupt change in belt aging degree and the increase in belt aging degree is normalized and used as the belt damage parameter at the end of the current work cycle.

[0009] Furthermore, the method for determining whether the belt is damaged at the end of the current work cycle based on belt damage parameters is as follows: When the belt damage parameter is greater than or equal to the preset belt damage parameter threshold, it is determined that the belt is damaged at the end of the current work cycle. When the belt damage parameter is less than the preset belt damage parameter threshold, it is determined that there is no belt damage at the end of the current work cycle.

[0010] Furthermore, the method for obtaining the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in a local image during the current work cycle is as follows: Binarize all local images in the current working loop, and use the highlighted pixels in the local images as target pixels. The target pixels in each local image are divided by distance to obtain the target category; Based on the positional distribution of target pixels in each target category, determine whether there is a belt breakage at the end of the current work cycle; The RANSAC algorithm is used to perform linear regression on the target pixels in each target category to obtain the center line of each target category. Based on the positional relationship of adjacent center lines in each local image, determine whether there is lateral deformation of the belt at the end of the current work cycle; Based on the distance between the target pixel in each target category and its center line, determine whether there is belt bending at the end of the current work cycle.

[0011] Furthermore, the method for determining whether a belt breakage has occurred at the end of the current work cycle is as follows: Scan the target pixels in each target category along the longitudinal direction with a preset step size. When no next target pixel appears within the preset step size, it is determined that there is a lateral breakage of the belt at the end of the current work cycle. When the next target pixel appears within the preset step size, it is determined that there is no lateral belt breakage at the end of the current work cycle. During the process of scanning the target pixels along the longitudinal direction with a preset step size, the difference in the horizontal coordinates of two adjacent target pixels is obtained and used as the first difference. When the first difference is greater than or equal to the preset longitudinal breakage threshold, it is determined that there is a longitudinal breakage of the belt at the end of the current work cycle. When the first difference is less than the preset longitudinal breakage threshold, it is determined that there is no longitudinal breakage of the belt at the end of the current work cycle.

[0012] Furthermore, the method for determining whether there is lateral deformation of the belt at the end of the current work cycle is as follows: Obtain the angle between two adjacent center lines in all local images in the current working loop, and use them as reference angles; When the reference angle is greater than or equal to the preset angle threshold, it is determined that there is lateral deformation of the belt at the end of the current work cycle; When all reference angles are less than the preset angle threshold, it is determined that there is no lateral deformation of the belt at the end of the current work cycle.

[0013] Furthermore, the method for determining whether there is lateral deformation of the belt at the end of the current work cycle also includes: Obtain the distance between two adjacent center lines in all local images in the current working loop, and use them as the first distance; Obtain the distance between two adjacent marked straight lines drawn longitudinally on the outer surface of the belt, and use this distance as the second distance; When the difference between the first distance and the second distance is greater than or equal to the preset distance threshold, it is determined that there is lateral deformation of the belt at the end of the current work cycle. When the difference between the first distance and the second distance is less than the preset distance threshold, it is determined that there is no lateral deformation of the belt at the end of the current work cycle.

[0014] Furthermore, the method for determining whether there is belt bending at the end of the current work cycle is as follows: For any target category, the distance between each target pixel in that category and its center line is obtained and used as the reference distance. When the variance of the reference distance is greater than or equal to the preset variance threshold, it is determined that there is belt bending at the end of the current work cycle; When the variance of the reference distance is less than the preset variance threshold, it is determined that there is no belt bending at the end of the current work cycle.

[0015] Secondly, another embodiment of the present invention provides a belt operation monitoring system for a tower-type pumping unit. The system includes a laser rangefinder and a high-speed camera installed below the platform of the tower-type pumping unit, a laser sensor reflector located directly below the laser rangefinder and installed on the upper surface of the counterweight, and the lens of the high-speed camera horizontally facing the outer surface of the belt. A wireless infrared temperature sensor is installed on the platform of the tower-type pumping unit with its temperature probe aligned with the belt. The belt operation monitoring system for the tower-type pumping unit further includes a data receiving module and a data processing module. The signal output terminals of all sensors and the high-speed camera are connected to the signal input terminal of the data receiving module, and the signal output terminal of the data receiving module is connected to the signal input terminal of the data processing module. The data receiving module is used to acquire in real time the counterweight distance, temperature data and local images of the belt of the tower pumping unit at each moment in each working cycle, as well as the average load of the belt in each working cycle; wherein, the counterweight distance is the distance between the counterweight and the upper platform; The data processing module is used to obtain the average counterweight distance of each work cycle based on the counterweight distance of the belt in each work cycle; and to obtain the belt aging degree at the end of each work cycle based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data and average load of each work cycle, and the initial length of the belt. Based on the belt aging level at the end of the current work cycle and the belt aging level at the end of each previous historical work cycle, obtain the belt damage parameters at the end of the current work cycle. Based on the belt damage parameters, determine whether there is belt damage at the end of the current work cycle. If damage is determined, obtain the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in the local image during the current work cycle.

[0016] Furthermore, before operation, a predetermined number of evenly spaced straight lines are drawn on the outer surface of the tower-type pumping unit's belt using light-colored rubber paint.

[0017] The present invention has the following beneficial effects: This invention uses a laser rangefinder to measure the position of the counterweight, avoiding the problems of complex structure of existing rope devices, potential belt wear from the rope, and inaccurate rope detection. This allows for accurate acquisition of the counterweight distance of the belt in each work cycle, and accurately obtains the average counterweight distance for each work cycle, indirectly reflecting the belt length change in each work cycle. This facilitates accurate analysis of the belt's potential damage at the end of each work cycle. Furthermore, based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data and average load of each work cycle, and the initial length of the belt, the aging degree of the belt at the end of each work cycle can be obtained, accurately reflecting the aging degree of the belt at the end of each work cycle. To analyze belt damage in real time, the damage parameters at the end of the current work cycle are obtained by comparing the belt aging degree at the end of the current work cycle with the belt aging degrees at the end of each previous historical work cycle, accurately reflecting the probability of belt damage at the end of the current work cycle, and facilitating timely and accurate detection of belt damage. For comprehensive... This invention identifies damage to belts by using a high-speed camera to monitor the surface coating of the belt and employing image recognition methods to automatically identify damage patterns in the surface coating. This effectively avoids the problems of manual labor, time-consuming processes, and inaccurate detection in existing technologies, improving the accuracy and comprehensiveness of belt damage detection. Therefore, this invention uses two early warning methods: longitudinal average strain measurement and surface coating photography. It simultaneously monitors and warns of overall belt aging, plastic deformation, and localized damage, enhancing the accuracy and reliability of belt monitoring and early warning results. Furthermore, based on belt damage parameters, it determines whether there is damage at the end of the current work cycle. If damage is detected, it obtains the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in a local image during the current work cycle. This timely detection of belt damage during operation and the issuance of specific alarms based on the corresponding damage status enable timely repair or replacement of the belt on the tower pumping unit, effectively ensuring the safety of equipment operation and operators, and guaranteeing the working efficiency of the tower pumping unit.

[0018] On the other hand, the laser rangefinder and high-speed camera in this invention can be quickly disassembled when there is no need for real-time monitoring and early warning of the belt. According to actual needs, the laser rangefinder or high-speed camera can be used for periodic inspection of the belts of multiple tower-type pumping units, saving a lot of resources. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the structure of a belt conveyor operation monitoring system for a tower-type pumping unit according to an embodiment of the present invention; Figure 2 This is a schematic flowchart illustrating a belt operation monitoring method for a tower-type pumping unit according to an embodiment of the present invention. Figure 3 This is a schematic diagram of a computer device provided according to an embodiment of the present invention.

[0021] Figure 1 In the diagram, 1 is the frame, 2 is the upper platform, 3 is the counterweight, 4 is the roller, 5 is the belt, 6 is the control cabinet, ① is the laser rangefinder, ② is the high-speed camera, ③ is the wireless infrared temperature sensor, ④ is the laser sensor reflector, ⑤ is the data receiving module, and ⑥ is the data processing module. Detailed Implementation

[0022] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a belt operation monitoring method and system for a tower-type pumping unit proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] This embodiment provides a belt conveyor operation monitoring system for a tower-type pumping unit, including a laser rangefinder ① and a high-speed camera ② installed below the upper platform 2 of the tower-type pumping unit, a laser sensor reflector ④ located directly below the laser rangefinder ① and installed on the upper surface of the counterweight 3, wherein the lens of the high-speed camera ② is horizontally oriented towards the outer surface of the belt 5, a wireless infrared temperature sensor ③ is installed on the upper platform 2 of the tower-type pumping unit with its temperature probe aligned with the belt, and also includes a data receiving module ⑤ and a data processing module ⑥. As a specific implementation, such as... Figure 1As shown, the belt conveyor operation monitoring system of the tower pumping unit includes a frame 1, which supports the belt conveyor structure of the entire tower pumping unit, an upper platform 2, a counterweight 3, a roller 4, a belt 5, a control cabinet 6, a laser rangefinder ①, a high-speed camera ②, a wireless infrared temperature sensor ③, a laser sensor reflector ④, a data receiving module ⑤, and a data processing module ⑥.

[0025] The laser rangefinder ① is connected to the data receiving module ⑤ inside the control cabinet 6 via a cable. The probe of the laser rangefinder ① is vertically downward, facing the laser sensor reflector ④, to measure the distance from the upper surface of the counterweight 3 to the laser rangefinder ①. In this embodiment, the laser rangefinder ① selected has a range greater than 10m, a measurement error less than ±5mm, a repeatability error less than ±2mm, and a measurement frequency greater than 100Hz.

[0026] A high-speed camera ② is installed below platform 2 of the tower-type pumping unit. The high-speed camera ② is connected to the data receiving module ⑤ inside the control cabinet 6 via a cable. The lens of the high-speed camera ② faces horizontally towards the outer surface of the conveyor belt 5. In this embodiment, a CCD high-speed camera is used, with a shooting range slightly wider than the width of the conveyor belt 5, a photo resolution greater than 1280×720, and a frame rate greater than 100.

[0027] A wireless infrared temperature sensor ③ is installed on platform 2 of the tower-type pumping unit. The temperature probe of the wireless infrared temperature sensor ③ is aligned with the belt 5 to measure the temperature of the belt 5 in real time. In this embodiment, an NB-IoT wireless infrared temperature sensor with an accuracy of 1℃ is used.

[0028] The laser sensor reflector ④ is mounted on the upper surface of the counterweight 3 and located directly below the laser rangefinder ①. This improves distance measurement accuracy and prevents interference from dust, water accumulation, surface tilt, and strong light on the surface of the counterweight 3. The laser sensor reflector ④ is marked with calibration points to calibrate the laser pulse direction of the laser rangefinder ①. In this embodiment, the SICK sensor reflector PL240DG is used.

[0029] The data receiving module ⑤ is installed inside the control cabinet 6 of the tower-type pumping unit. It can be connected to sensors and other devices via wired or wireless means to control the opening and closing of the sensors and other data acquisition devices, receive sensor data in real time, and transmit the data to the data processing module ⑥. Specifically, the signal output terminals of all sensors and high-speed cameras are connected to the signal input terminal of the data receiving module ⑤, and the signal output terminal of the data receiving module ⑤ is connected to the signal input terminal of the data processing module ⑥. Therefore, in this embodiment, the data receiving module ⑤ acquires in real time the counterweight distance, temperature data, and local images of the belt 5 of the tower-type pumping unit at each moment in each working cycle, as well as the average load of the belt 5 in each working cycle; where the counterweight distance is the distance between the counterweight 3 and the upper platform 2. In this embodiment, the time interval between two adjacent moments is set to 2 seconds. The implementer can set the time interval between two adjacent moments according to the actual situation; it is not limited here. However, it should be noted that there must be no discontinuity between the two local images of the belt 5 acquired at two adjacent moments.

[0030] The data processing module ⑥ can be installed away from the tower-type pumping unit and includes a data processing unit and an alarm unit. The data processing unit can simultaneously receive and process data transmitted by multiple data receiving modules ⑤. The data processing unit determines the damage status of the belt 5. When damage to the belt 5 is determined, the alarm unit issues a corresponding alarm signal based on the damage status of the belt 5. Therefore, in this embodiment, the data processing module ⑥ is used to obtain the average counterweight distance of each working cycle based on the counterweight distance of the belt 5 in each working cycle; to obtain the belt aging degree at the end of each working cycle based on the difference in average counterweight distance between each working cycle and the first working cycle, the temperature data and average load of each working cycle, and the initial length of the belt 5; to obtain the belt damage parameters at the end of the current working cycle based on the belt aging degree at the end of the current working cycle and the belt aging degree at the end of each previous historical working cycle; and to determine whether there is damage to the belt 5 at the end of the current working cycle based on the belt damage parameters. If damage is determined, the belt damage status at the end of the current working cycle is obtained based on the grayscale values ​​of the pixels in the local image of the current working cycle. The alarm unit will issue corresponding alarms based on the damage of the belt, which helps staff to promptly identify the specific damage to belt 5 of the tower-type pumping unit, thereby facilitating accurate and efficient maintenance by maintenance personnel.

[0031] To accurately analyze the damage to belt 5 later, in this embodiment, before the tower-type pumping unit's belt 5 is in operation and in good condition, a predetermined number of evenly spaced straight lines are drawn on the outer surface of belt 5 using light-colored rubber paint. In this embodiment, the predetermined number is set to 4. The implementer can set the size of the predetermined number according to the actual situation, and it is not limited here.

[0032] To illustrate in detail the specific process of damage detection for the belts of a tower-type pumping unit during operation, this embodiment proposes a method for monitoring the operation of the belts in a tower-type pumping unit. Please refer to [link to relevant documentation]. Figure 2 The diagram illustrates a schematic flowchart of a belt conveyor operation monitoring method for a tower-type pumping unit according to an embodiment of the present invention. The method includes the following steps: Step S1: Real-time acquisition of counterweight distance, temperature data and local images of the belt of the tower pumping unit at each moment in each working cycle, as well as the average load of the belt in each working cycle; wherein, the counterweight distance is the distance between the counterweight and the upper platform.

[0033] Specifically, in actual operation, the belt of the tower pumping unit operates in a reciprocating cycle. In order to improve the efficiency of analyzing damage to belt 5, this embodiment takes each working cycle of belt 5 of the tower pumping unit as an example for analysis. The damage of belt 5 of the tower pumping unit after each working cycle is analyzed in real time. Real-time detection of damage to belt 5 is beneficial for timely repair of belt 5 and ensures that the tower pumping unit maintains normal operation.

[0034] To accurately analyze the damage to belt 5 after each work cycle, this embodiment uses a laser rangefinder ① to acquire the counterweight distance of belt 5 at each moment in each work cycle of the tower-type pumping unit, where the counterweight distance is the distance between counterweight 3 and upper platform 2; a wireless infrared temperature sensor ③ to acquire the temperature data of belt 5 at each moment in each work cycle of the tower-type pumping unit; and a high-speed camera ② to acquire local images of belt 5 at each moment in each work cycle of the tower-type pumping unit. The local images from all moments in each work cycle can be stitched together to form a complete belt 5. It should be noted that the subsequent local images are all grayscale images; grayscale processing is a known technique and will not be elaborated further. Based on the duration and counterweight of each work cycle, the average load of each work cycle is obtained; the method for obtaining the average load is a known technique and will not be elaborated further. Subsequently, based on the counterweight distance, temperature data, local images, and average load of belt 5 in each work cycle, the damage to belt 5 after each work cycle is analyzed.

[0035] Step S2: Based on the counterweight distance of the belt in each working cycle, obtain the average counterweight distance of each working cycle; based on the difference in average counterweight distance between each working cycle and the first working cycle, the temperature data and average load of each working cycle, and the initial length of the belt, obtain the belt aging degree at the end of each working cycle.

[0036] Specifically, under normal circumstances, with the same counterweight 3, the change in counterweight distance of belt 5 in each working cycle of a tower-type pumping unit is the same. However, in reality, belt 5 gradually suffers irreversible damage with continuous operation. When belt 5 is damaged, the change in counterweight distance in each working cycle will be significantly larger than the change in counterweight distance in previous working cycles. Furthermore, when the damage to belt 5 reaches a certain level, belt 5 may break, affecting the operation of the tower-type pumping unit. To avoid affecting the operation of the tower-type pumping unit, this embodiment first obtains the average counterweight distance of each working cycle based on the counterweight distance of the belt in each working cycle. It is known that the average counterweight distance of belt 5 in the first working cycle is the most normal, at which point belt 5 is intact and assumed to be undamaged. Then, based on the difference in average counterweight distance between each working cycle and the first working cycle, the temperature data and average load of each working cycle, and the initial length of belt 5, the degree of belt aging at the end of each working cycle is obtained. The greater the degree of belt aging, the greater the possibility that belt 5 is damaged at the end of the corresponding working cycle. It should be noted that the initial length of belt 5 is essentially the length of a brand-new belt under no-load conditions.

[0037] Preferably, in one feasible embodiment, the method for obtaining the average counterweight distance is as follows: for any working cycle of the belt 5, the average counterweight distance of that working cycle is obtained based on the counterweight distance in that working cycle; wherein, the formula for calculating the average counterweight distance is: In the formula, The average counterweight distance during the c-th work cycle; Let c be the duration of the c-th work cycle; The distance of the counterweight at time t in the c-th work cycle; To perform calculus on the counterweight distance in the c-th work cycle.

[0038] At this point, the average counterweight distance for each work cycle is obtained.

[0039] Preferably, in one feasible embodiment, the method for obtaining the belt aging degree is as follows: For any working cycle of belt 5, the difference between the average counterweight distance of this working cycle and the first working cycle is obtained as a first value; the larger the first value, the more severe the accumulated material aging of the belt, indirectly indicating that the belt 5 is more likely to be damaged at the end of the working cycle; in order to further analyze the possibility of belt 5 being damaged at the end of the working cycle, the ratio of the first value to the initial length is obtained as the average strain increment at the end of the working cycle; it is known that the average strain of the standard belt is different under different temperatures and different average loads for different working cycles, and obtaining the average belt strain through temperature and average load is a well-known technique, which will not be elaborated further. Therefore, in this embodiment, the average value of the temperature data at all times in the working cycle is used as the target temperature data of the working cycle; the average strain of the standard belt in the working cycle is obtained through the target temperature data and average load of the working cycle; then the ratio of the average strain increment at the end of the working cycle to the average strain of the standard belt in the working cycle is used as the belt aging degree at the end of the working cycle, accurately reflecting the aging degree of belt 5 at the end of the working cycle.

[0040] At this point, the belt aging degree of belt 5 at the end of each working cycle is obtained.

[0041] Step S3: Based on the belt aging degree at the end of the current work cycle and the belt aging degree at the end of each previous historical work cycle, obtain the belt damage parameters at the end of the current work cycle.

[0042] Specifically, during the monitoring of the belt operation of the tower-type pumping unit, if there is no damage on belt 5, the degree of belt aging at the end of the work cycle will be similar; if there is damage on belt 5, the degree of belt aging at the end of the corresponding work cycle will be significantly increased. To analyze whether damage has occurred on belt 5 in real time, this embodiment obtains the belt damage parameter at the end of the current work cycle based on the belt aging degree at the end of the current work cycle and the belt aging degree at the end of each previous historical work cycle. The larger the belt damage parameter, the greater the possibility that there is damage in belt 5 at the end of the current work cycle.

[0043] Preferably, in one feasible embodiment of this invention, the method for obtaining the belt damage parameters is as follows: The belt aging degree at the end of the current work cycle is arranged in the order of the work cycles along with the belt aging degree at the end of each previous historical work cycle to obtain a belt aging degree sequence; that is, the belt aging degree from the first work cycle to the end of the current work cycle is constructed into a belt aging degree sequence. To analyze the changes in belt aging degree and thus the damage status of belt 5 at the end of the current work cycle, and to accurately determine whether belt 5 is damaged at the end of the current work cycle, this embodiment fits the elements in the belt aging degree sequence into a curve, obtains the tangent slope of each belt aging degree on the curve, and then divides the tangent slope using the maximum inter-class variance to obtain a first category and a second category; wherein, curve fitting and maximum inter-class variance are well-known techniques and will not be elaborated further. In reality, the damage degree of belt 5 increases progressively, and there will not be a situation where the belt aging degree at the end of a certain work cycle is less than the belt aging degree at the end of any previous work cycle. In order to analyze the belt damage parameters at the end of the current work cycle, and then obtain the absolute value of the difference between the mean of all tangent slopes in the first category and the mean of all tangent slopes in the second category, as the belt aging mutation degree at the end of the current work cycle, the greater the belt aging mutation degree, the more likely the belt 5 is to be damaged at the end of the current work cycle. To more accurately analyze the possibility of belt 5 being damaged at the end of the current work cycle, the absolute value of the difference between the standard deviations of all tangent slopes in the first category and the standard deviations of all tangent slopes in the second category is obtained. This difference is used as the degree of belt aging increase at the end of the current work cycle. The greater the degree of belt aging increase, the greater the possibility of belt 5 being damaged at the end of the current work cycle. Therefore, in this embodiment, the sum of the belt aging mutation degree and the belt aging increase degree is normalized and used as the belt damage parameter at the end of the current work cycle. In this embodiment, the sum of the belt aging mutation degree and the belt aging increase degree is normalized using the norm normalization function.

[0044] Step S4: Determine whether there is any damage to the belt at the end of the current work cycle based on the belt damage parameters. If damage is determined, obtain the belt damage status at the end of the current work cycle based on the grayscale values ​​of the pixels in the local image during the current work cycle.

[0045] It is known that the larger the belt damage parameter, the greater the probability that belt 5 will be damaged at the end of the current work cycle. Therefore, this embodiment determines whether the belt is damaged at the end of the current work cycle based on the belt damage parameter. If damage is determined to exist, the specific damage condition of belt 5 is further analyzed. It is known that marked straight lines are drawn on the outer surface of belt 5, and the pixels corresponding to the marked lines are highlighted pixels in the local image. When belt 5 is damaged, the marked straight lines will change. Among them, the damage conditions of belt 5 are usually belt breakage, belt lateral deformation, and belt bending. Therefore, this embodiment obtains the belt damage condition at the end of the current work cycle based on the grayscale values ​​of the pixels in the local image during the current work cycle.

[0046] Preferably, in one feasible embodiment, the method for determining whether the belt is damaged at the end of the current work cycle based on the belt damage parameter is as follows: In this embodiment, a preset belt damage parameter threshold is set to 0.5. The implementer can set the size of the preset belt damage parameter threshold according to the actual situation, which is not limited here. When the belt damage parameter is greater than or equal to the preset belt damage parameter threshold, it is determined that the belt is damaged at the end of the current work cycle; when the belt damage parameter is less than the preset belt damage parameter threshold, it is determined that the belt is not damaged at the end of the current work cycle.

[0047] Preferably, in one feasible method of this embodiment, the method for obtaining the belt damage status at the end of the current work cycle is as follows: All local images in the current work cycle are binarized, and the highlighted pixels in the local images are taken as target pixels; wherein, binarization is a well-known technique and will not be elaborated further. The K-means clustering algorithm is used to divide the target pixels in each local image by distance to obtain the target category. In this embodiment, the k value in the K-means clustering algorithm is set to 4, which should be consistent with the number of marked lines drawn; this indirectly reflects that the target pixels in a target category in a local image are pixels from the same marked line. The K-means clustering algorithm is a well-known technique and will not be elaborated further. In reality, belt 5 may have transverse or longitudinal breaks. Therefore, this embodiment determines whether belt breakage occurs at the end of the current work cycle based on the positional distribution of target pixels in each target category. Specifically, it scans the target pixels in each target category along the longitudinal direction, i.e., the direction of the marked line, with a preset step size. If no next target pixel appears within the preset step size, it indicates that the marked line has a break, and it is determined that there is a transverse breakage of the belt at the end of the current work cycle. The alarm unit in the data processing module ⑥ issues an alarm signal for transverse breakage of belt 5. Conversely, if the next target pixel appears within the preset step size, it is determined that there is no transverse breakage of the belt at the end of the current work cycle. During the process of scanning target pixels along the longitudinal direction with a preset step size, the absolute value of the difference between the horizontal coordinates of two adjacent target pixels is obtained, and both are used as the first difference. When the first difference is greater than or equal to the preset longitudinal breakage threshold, it indicates that there is a longitudinal breakage in the belt part corresponding to the local image, causing the target pixels in the same target category to deviate, and thus there is a longitudinal breakage of the belt at the end of the current work cycle. The alarm unit in the data processing module ⑥ issues an alarm signal for the longitudinal breakage of belt 5. Conversely, when the first difference is less than the preset longitudinal breakage threshold, it is determined that there is no longitudinal breakage of the belt at the end of the current work cycle. It should be noted that in this embodiment, the preset step size is set to 5 pixels and the preset longitudinal breakage threshold is set to 50 pixels. Implementers can set the preset step size and preset longitudinal breakage threshold according to the actual situation, and there is no limitation here. To analyze whether belt 5 exhibits lateral deformation during the current work cycle, this embodiment first performs linear regression on the target pixels in each target category using the RANSAC algorithm to obtain the center line of each target category. The RANSAC algorithm is a well-known technique and will not be elaborated further. Normally, adjacent center lines in the same local image are parallel. Therefore, this embodiment determines whether lateral deformation of the belt exists at the end of the current work cycle based on the positional relationship of adjacent center lines in each local image. Specifically, it obtains the angle between two adjacent center lines in all local images during the current work cycle, using these angles as reference angles. The smaller the reference angle, the more parallel the two adjacent center lines are. Therefore, this embodiment sets a preset angle threshold. When a reference angle is greater than or equal to the preset angle threshold, it is determined that lateral deformation of the belt exists at the end of the current work cycle; the alarm unit in the data processing module ⑥ issues an alarm signal for lateral deformation of belt 5. Conversely, when all reference angles are less than the preset angle threshold, it is determined that lateral deformation of the belt does not exist at the end of the current work cycle. This embodiment sets the preset angle threshold to 5°. Implementers can set the size of the preset angle threshold according to actual conditions, and this is not limited here. In another embodiment, the distance between two adjacent center lines in all local images of the current work cycle is obtained as the first distance; the distance between two adjacent marked lines drawn longitudinally on the outer surface of the belt is obtained as the second distance; since the marked lines are drawn uniformly, the distance between any two adjacent marked lines is the same. The method for obtaining the distance between the two lines is a well-known technique and will not be described in detail here. When the first distance and the second distance are significantly different, it indicates a greater likelihood of lateral deformation of the belt 5 at the end of the current work cycle. Therefore, when the absolute value of the difference between the first distance and the second distance is greater than or equal to a preset distance threshold, it is determined that lateral deformation of the belt exists at the end of the current work cycle, and the alarm unit in the data processing module ⑥ issues an alarm signal for lateral deformation of the belt 5; conversely, when the absolute value of the difference between the first distance and the second distance is less than the preset distance threshold, it is determined that lateral deformation of the belt does not exist at the end of the current work cycle. In this embodiment, the preset distance threshold is set to 30 pixels. Implementers can set the size of the preset distance threshold according to actual conditions, and this is not limited here. To analyze whether belt 5 is bent in the current work cycle, it is known that when belt 5 is bent, the horizontal coordinate of target pixels in the same target category will fluctuate significantly. Therefore, this embodiment determines whether belt bending exists at the end of the current work cycle based on the distance between the target pixels in each target category and their center line. Specifically: for any target category, the distance between each target pixel in that category and its center line is obtained and used as a reference distance; when the variance of the reference distance is greater than or equal to a preset variance threshold, it is determined that belt bending exists at the end of the current work cycle, and the alarm unit in the data processing module ⑥ issues an alarm signal for belt 5 bending. Conversely, when the variance of the reference distance is less than the preset variance threshold, it is determined that belt bending does not exist at the end of the current work cycle. This embodiment sets the preset variance threshold to be... The implementer can set the size of the preset variance threshold according to the actual situation, and there is no limit here.

[0048] Thus, the damage to belt 5 during operation was detected in a timely manner, and specific alarms were triggered based on the corresponding damage conditions. This enabled staff to promptly repair or replace the belt of the tower-type pumping unit, effectively ensuring the safety of equipment operation and operators.

[0049] This embodiment uses a laser rangefinder ① to measure the position of the counterweight 3, avoiding the problems of complex structure of the lazy rope device, potential belt wear by the lazy rope, and inaccurate detection of the lazy rope in the prior art. A high-speed camera ② monitors the surface coating of the belt 5, and image recognition methods are used to automatically identify the damage patterns of the surface coating of the belt 5, effectively avoiding the problems of manual labor, time-consuming process, and inaccurate detection in the prior art. This embodiment uses two early warning methods: longitudinal average strain measurement of the belt 5 and surface coating photography. It can simultaneously monitor and warn of overall aging, plastic deformation, and local damage of the belt 5, enhancing the accuracy and reliability of the monitoring and early warning results. Since the damage to the belt 5 of a tower-type pumping unit is a slow process, the laser rangefinder ① and high-speed camera ② in this embodiment can be quickly disassembled when real-time monitoring and early warning of the belt 5 are not required. Depending on actual needs, the laser rangefinder ① or high-speed camera ② can be used for periodic inspection of belts of multiple tower-type pumping units, saving significant resources.

[0050] In summary, this embodiment acquires the counterweight distance, temperature data, and local images of the belt at each moment, as well as the average load of each work cycle; it obtains the average counterweight distance based on the counterweight distance; and it obtains the belt aging degree based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data of each work cycle, and the average load. Furthermore, it obtains the belt damage parameters at the end of the current work cycle to determine if the belt is damaged. If damage is determined, it obtains the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in the local images of the current work cycle. This invention, through the counterweight distance and local images of the belt in each work cycle, more accurately, comprehensively, and promptly analyzes the damage status of the belt, ensuring the working efficiency of the tower-type pumping unit.

[0051] In addition, this embodiment also protects a computer device; please refer to [link to relevant documentation]. Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned methods for monitoring the belt operation of a tower-type pumping unit.

[0052] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for monitoring belt operation of a tower-type pumping unit, characterized in that, The method includes the following steps: The system acquires real-time data on the counterweight distance, temperature, and local images of the belt of the tower-type pumping unit at each moment during each work cycle, as well as the average load on the belt during each work cycle; where the counterweight distance is the distance between the counterweight and the upper platform. Based on the counterweight distance of the belt in each work cycle, obtain the average counterweight distance of each work cycle; based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data and average load of each work cycle, and the initial length of the belt, obtain the belt aging degree at the end of each work cycle. Based on the belt aging level at the end of the current work cycle and the belt aging level at the end of each previous historical work cycle, obtain the belt damage parameters at the end of the current work cycle. Based on the belt damage parameters, determine whether there is belt damage at the end of the current work cycle. If damage is determined, obtain the belt damage status at the end of the current work cycle based on the gray values ​​of pixels in the local image during the current work cycle. The method for obtaining the degree of belt aging is as follows: For any working cycle of the belt, obtain the difference between the average counterweight distance of this working cycle and the first working cycle, and use it as the first value; The ratio of the first value to the initial length is taken as the average strain increment at the end of the working cycle. The average of the temperature data at all times in the work cycle is used as the target temperature data for the work cycle. The standard belt average strain for this working cycle is obtained by using the target temperature data and average load for this working cycle. The ratio of the average strain increment to the average strain of the standard belt is used as the belt aging degree at the end of the working cycle. The method for obtaining the belt damage parameters is as follows: The belt aging degree at the end of the current work cycle is arranged with the belt aging degree at the end of each previous historical work cycle according to the order of the work cycles to obtain the belt aging degree sequence. The elements in the belt aging degree sequence are fitted into a curve, and the tangent slope of each belt aging degree on the curve is obtained. The tangent slope is divided by the maximum inter-class variance to obtain the first category and the second category. The difference between the mean of all tangent slopes in the first category and the mean of all tangent slopes in the second category is taken as the degree of belt aging mutation at the end of the current work cycle. The difference between the standard deviation of all tangent slopes in the first category and the standard deviation of all tangent slopes in the second category is taken as the degree of belt aging increase at the end of the current work cycle; The sum of the abrupt change in belt aging degree and the increase in belt aging degree is normalized and used as the belt damage parameter at the end of the current work cycle.

2. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 1, characterized in that, The method for obtaining the average counterweight distance is as follows: For any working cycle of the belt, the average counterweight distance of that working cycle is obtained based on the counterweight distance in that working cycle; The formula for calculating the average counterweight distance is as follows: In the formula, The average counterweight distance during the c-th work cycle; Let c be the duration of the c-th work cycle; The distance of the counterweight at time t in the c-th work cycle; To perform calculus on the counterweight distance in the c-th work cycle.

3. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 1, characterized in that, The method for determining whether the belt is damaged at the end of the current work cycle based on belt damage parameters is as follows: When the belt damage parameter is greater than or equal to the preset belt damage parameter threshold, it is determined that the belt is damaged at the end of the current work cycle. When the belt damage parameter is less than the preset belt damage parameter threshold, it is determined that there is no belt damage at the end of the current work cycle.

4. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 1, characterized in that, The method for obtaining the belt damage status at the end of the current work cycle based on the grayscale values ​​of pixels in a local image during the current work cycle is as follows: Binarize all local images in the current working loop, and use the highlighted pixels in the local images as target pixels. The target pixels in each local image are divided by distance to obtain the target category; Based on the positional distribution of target pixels in each target category, determine whether there is a belt breakage at the end of the current work cycle; The RANSAC algorithm is used to perform linear regression on the target pixels in each target category to obtain the center line of each target category. Based on the positional relationship of adjacent center lines in each local image, determine whether there is lateral deformation of the belt at the end of the current work cycle; Based on the distance between the target pixel in each target category and its center line, determine whether there is belt bending at the end of the current work cycle.

5. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 4, characterized in that, The method for determining whether a belt breakage has occurred at the end of the current work cycle is as follows: Scan the target pixels in each target category along the longitudinal direction with a preset step size. When no next target pixel appears within the preset step size, it is determined that there is a lateral breakage of the belt at the end of the current work cycle. When the next target pixel appears within the preset step size, it is determined that there is no lateral belt breakage at the end of the current work cycle. During the process of scanning the target pixels along the longitudinal direction with a preset step size, the difference in the horizontal coordinates of two adjacent target pixels is obtained and used as the first difference. When the first difference is greater than or equal to the preset longitudinal breakage threshold, it is determined that there is a longitudinal breakage of the belt at the end of the current work cycle. When the first difference is less than the preset longitudinal breakage threshold, it is determined that there is no longitudinal breakage of the belt at the end of the current work cycle.

6. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 4, characterized in that, The method for determining whether there is lateral deformation of the belt at the end of the current work cycle is as follows: Obtain the angle between two adjacent center lines in all local images in the current working loop, and use them as reference angles; When the reference angle is greater than or equal to the preset angle threshold, it is determined that there is lateral deformation of the belt at the end of the current work cycle; When all reference angles are less than the preset angle threshold, it is determined that there is no lateral deformation of the belt at the end of the current work cycle.

7. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 6, characterized in that, The method for determining whether there is lateral deformation of the belt at the end of the current work cycle also includes: Obtain the distance between two adjacent center lines in all local images in the current working loop, and use them as the first distance; Obtain the distance between two adjacent marked straight lines drawn longitudinally on the outer surface of the belt, and use this distance as the second distance; When the difference between the first distance and the second distance is greater than or equal to the preset distance threshold, it is determined that there is lateral deformation of the belt at the end of the current work cycle. When the difference between the first distance and the second distance is less than the preset distance threshold, it is determined that there is no lateral deformation of the belt at the end of the current work cycle.

8. The belt conveyor operation monitoring method for a tower-type pumping unit as described in claim 4, characterized in that, The method for determining whether there is belt bending at the end of the current work cycle is as follows: For any target category, the distance between each target pixel in that category and its center line is obtained and used as the reference distance. When the variance of the reference distance is greater than or equal to the preset variance threshold, it is determined that there is belt bending at the end of the current work cycle; When the variance of the reference distance is less than the preset variance threshold, it is determined that there is no belt bending at the end of the current work cycle.

9. A belt conveyor operation monitoring system for a tower-type pumping unit, comprising a laser rangefinder and a high-speed camera installed below the upper platform of the tower-type pumping unit, a laser sensor reflector located directly below the laser rangefinder and installed on the upper surface of the counterweight, the lens of the high-speed camera horizontally facing the outer surface of the belt, and a wireless infrared temperature sensor installed on the upper platform of the tower-type pumping unit with its temperature probe aligned with the belt, characterized in that, The belt conveyor operation monitoring system of the tower pumping unit also includes a data receiving module and a data processing module; the signal output terminals of all sensors and high-speed cameras are connected to the signal input terminal of the data receiving module, and the signal output terminal of the data receiving module is connected to the signal input terminal of the data processing module. The data receiving module is used to acquire in real time the counterweight distance, temperature data and local images of the belt of the tower pumping unit at each moment in each working cycle, as well as the average load of the belt in each working cycle; wherein, the counterweight distance is the distance between the counterweight and the upper platform; The data processing module is used to obtain the average counterweight distance of each work cycle based on the counterweight distance of the belt in each work cycle; and to obtain the belt aging degree at the end of each work cycle based on the difference in average counterweight distance between each work cycle and the first work cycle, the temperature data and average load of each work cycle, and the initial length of the belt. Based on the belt aging level at the end of the current work cycle and the belt aging level at the end of each previous historical work cycle, obtain the belt damage parameters at the end of the current work cycle. Based on the belt damage parameters, determine whether there is belt damage at the end of the current work cycle. If damage is determined, obtain the belt damage status at the end of the current work cycle based on the gray values ​​of pixels in the local image during the current work cycle. The method for obtaining the degree of belt aging is as follows: For any working cycle of the belt, obtain the difference between the average counterweight distance of this working cycle and the first working cycle, and use it as the first value; The ratio of the first value to the initial length is taken as the average strain increment at the end of the working cycle. The average of the temperature data at all times in the work cycle is used as the target temperature data for the work cycle. The standard belt average strain for this working cycle is obtained by using the target temperature data and average load for this working cycle. The ratio of the average strain increment to the average strain of the standard belt is used as the belt aging degree at the end of the working cycle. The method for obtaining the belt damage parameters is as follows: The belt aging degree at the end of the current work cycle is arranged with the belt aging degree at the end of each previous historical work cycle according to the order of the work cycles to obtain the belt aging degree sequence. The elements in the belt aging degree sequence are fitted into a curve, and the tangent slope of each belt aging degree on the curve is obtained. The tangent slope is divided by the maximum inter-class variance to obtain the first category and the second category. The difference between the mean of all tangent slopes in the first category and the mean of all tangent slopes in the second category is taken as the degree of belt aging mutation at the end of the current work cycle. The difference between the standard deviation of all tangent slopes in the first category and the standard deviation of all tangent slopes in the second category is taken as the degree of belt aging increase at the end of the current work cycle; The sum of the abrupt change in belt aging degree and the increase in belt aging degree is normalized and used as the belt damage parameter at the end of the current work cycle.

10. The belt conveyor operation monitoring system for a tower-type pumping unit as described in claim 9, characterized in that, Before operation, the belt of the tower-type pumping unit is marked with a predetermined number of evenly spaced straight lines using light-colored rubber paint on the outer surface of the belt.

Images